Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered structurally. The description adds real value on top by stating the blast radius (only the edge, not the linked objects) and irreversibility ("Unwiderruflich"). It omits permission/auth requirements and what a successful response looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The German core is well front-loaded and dense: purpose, non-destructive scope, irreversibility, inverse tool — four useful sentences in a row. But the trailing "| EN: object, record, entry, property, link, search" keyword list is SEO padding that earns no place, and the description is delivered in German where the tool title and schema are English, adding avoidable parsing cost.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter destructive mutation with full annotation coverage and no output schema, the description covers what is destroyed and that it cannot be undone. It leaves the agent guessing how to obtain a valid link_udid and whether ontoname/scope context is required — a noticeable gap for a delete call where a wrong id is unrecoverable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single parameter, so the schema documents link_udid and the baseline of 3 applies. The description adds nothing about where a link_udid comes from (e.g. onto_object_show or onto_object_graph) or its format, so it does not compensate beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Verknuepfung zwischen zwei Objekten entfernen") and immediately scopes it against the most confusable sibling by clarifying that only the edge is removed, "NICHT die beteiligten Objekte" — which distinguishes it from onto_object_delete. An agent can select it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It names one related tool, onto_object_create_link, as the inverse operation ("Zum Anlegen derselben Kante"), which gives partial routing guidance. However it never addresses the closest ambiguity — when to delete-and-recreate versus use onto_object_update_link — and gives no prerequisites, so usage is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.